© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 44223
    Prev
    Next
    INDEX
    Explanations

    terminology associated with sieges and encirclements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    siege and surrounded by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solches
    -0.31
     du
    -0.31
     doInBackground
    -0.30
    íncipe
    -0.29
    SQLiteDatabase
    -0.28
     darunter
    -0.28
    lucas
    -0.28
    Discografia
    -0.28
     detriment
    -0.28
    THISDAY
    -0.28
    POSITIVE LOGITS
    SequentialGroup
    0.94
     siege
    0.94
     besieged
    0.82
     Siege
    0.77
     AssemblyCompany
    0.75
     besie
    0.69
    Siege
    0.68
     للاسماء
    0.64
    AddTagHelper
    0.63
     '\\;'
    0.62
    Activations Density 0.034%

    No Known Activations